表情识别求助 #622
Labels
No Label
bug
duplicate
enhancement
help wanted
invalid
question
wontfix
No Milestone
No project
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: HswOAuth/llm_course#622
Loading…
Reference in New Issue
Block a user
No description provided.
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
想开发一款用在手机端的表情识别程序,基于图片和声音融合识别表情,图片数据集基于fer2013,目前尝试了很多种方法,图片识别率最多只能达到65%。声音识别率更低,有没有可以参考的例子或者方向提供一下。
可以参考下:emotion-recognition、speech-emotion-recognition
https://paperswithcode.com/task/emotion-recognition
https://paperswithcode.com/task/speech-emotion-recognition
https://arxiv.org/abs/2407.18552
感谢老师的回复。
我看到链接(https://paperswithcode.com/task/emotion-recognition)里的github地址中的https://github.com/MahmoudRabea13/IdentiFace,用于fer2013数据集的识别率如下:
Emotion Recognition 81.26% 66.13%
训练集和验证集的差别有点大,我之前也有过类似的结果,这种是否是过拟合了。
另外,fer2013这个数据集是不是最好的也只能是这个水平了。